<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Fabrica Technology — Ken Ono</title><description>Thoughts on fractional CTO work, architecture, AI, and building products.</description><link>https://fabrica.tech/</link><item><title>Delete or Tweak Your Skills to See How Well They Work</title><link>https://fabrica.tech/blog/delete-or-tweak-your-skills-to-see-how-well-they-work/</link><guid isPermaLink="true">https://fabrica.tech/blog/delete-or-tweak-your-skills-to-see-how-well-they-work/</guid><description>The papers say agent context files cost more and don&apos;t reliably help — but the honest answer depends on your repo and your model. Here&apos;s a cheap way to measure your own setup, using features you&apos;re already shipping.</description><pubDate>Fri, 26 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Your Local Dev Environment Needs an API</title><link>https://fabrica.tech/blog/local-dev-env-needs-api/</link><guid isPermaLink="true">https://fabrica.tech/blog/local-dev-env-needs-api/</guid><description>Process-compose and a thin wrapper gave my local dev stack one control plane for humans and agents — real readiness, structured status, and parallel worktrees without port collisions.</description><pubDate>Fri, 12 Jun 2026 00:00:00 GMT</pubDate></item><item><title>An Evidence-First Scorecard for AI Engineering</title><link>https://fabrica.tech/blog/ai-engineering-maturity-scorecard/</link><guid isPermaLink="true">https://fabrica.tech/blog/ai-engineering-maturity-scorecard/</guid><description>An evidence-first AI engineering scorecard for small teams: have the agent inspect the repo, workflow evidence, automations, and agent instructions before asking humans how mature they feel.</description><pubDate>Sat, 23 May 2026 00:00:00 GMT</pubDate></item><item><title>Native from Web — When the Spec Is Already Running</title><link>https://fabrica.tech/blog/native-from-web-spec/</link><guid isPermaLink="true">https://fabrica.tech/blog/native-from-web-spec/</guid><description>Using a working web app as the behavioral spec for an Expo React Native app: hooks vs components, when cheaper models break down, and why parity needs a written trail for the next agent.</description><pubDate>Tue, 12 May 2026 00:00:00 GMT</pubDate></item><item><title>Making SuperSubset: It&apos;s All About the Spec</title><link>https://fabrica.tech/blog/making-supersubset/</link><guid isPermaLink="true">https://fabrica.tech/blog/making-supersubset/</guid><description>Building SuperSubset taught me that the bottleneck in agentic development is the spec. The charts looked great. The tests passed. The product still failed.</description><pubDate>Sun, 03 May 2026 00:00:00 GMT</pubDate></item><item><title>Stop Thinking in Prompts. Start Thinking in Skills.</title><link>https://fabrica.tech/blog/think-in-skills/</link><guid isPermaLink="true">https://fabrica.tech/blog/think-in-skills/</guid><description>How to get more out of AI by treating skills — not prompts — as the unit of leverage. Lessons from a workshop on agentic engineering.</description><pubDate>Fri, 24 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Hello World: I Had AI Interview Me to Write This Post</title><link>https://fabrica.tech/blog/hello-world/</link><guid isPermaLink="true">https://fabrica.tech/blog/hello-world/</guid><description>I built a system where AI interviews me instead of writing for me. Did the first interview hands-free while driving. Here&apos;s how it works.</description><pubDate>Wed, 15 Apr 2026 00:00:00 GMT</pubDate></item></channel></rss>